Sentiment Analysis on IMDB Counterfactual (test)
98AccuracyXLNet-Large
Evaluation Results
| Method | Links | |
|---|---|---|
| XLNet-LargeParameter=340M, Training Set=Counterfactual (CF)2021.06 | 98 | |
| WWM-BERT-LargeParameter=335M, Training Set=Counterfactual (CF)2021.06 | 96.9 | |
| XLNet-LargeParameter=340M, Training Set=Combined (C)2021.06 | 96.9 | |
| ROBERTa-LargeParameter=355M, Training Set=Counterfactual (CF)2021.06 | 96.9 | |
| ROBERTa-LargeParameter=355M, Training Set=Combined (C)2021.06 | 96.7 | |
| XLNet-LargeParameter=340M, Training Set=Augmented (AC)2021.06 | 95.5 | |
| WWM-BERT-LargeParameter=335M, Training Set=Combined (C)2021.06 | 95.3 | |
| BERTParameter=110M, Training Set=Combined (C)2021.06 | 95.1 | |
| ROBERTa-LargeParameter=355M, Training Set=Augmented (AC)2021.06 | 94.3 | |
| WWM-BERT-LargeParameter=335M, Training Set=Augmented (AC)2021.06 | 94.1 | |
| XLNet-LargeParameter=340M, Training Set=Original (O)2021.06 | 93.9 | |
| WWM-BERT-LargeParameter=335M, Training Set=Original (O)2021.06 | 93 | |
| ROBERTa-LargeParameter=355M, Training Set=Original (O)2021.06 | 93 | |
| BERTParameter=110M, Training Set=Augmented (AC)2021.06 | 92.2 | |
| Bi-LSTMParameter=0.2M, Training Set=Combined (C)2021.06 | 92 | |
| SVM(TF-IDF)Training Set=Counterfactual (CF)2021.06 | 91.2 | |
| BERTParameter=110M, Training Set=Counterfactual (CF)2021.06 | 90.8 | |
| Bi-LSTMParameter=0.2M, Training Set=Counterfactual (CF)2021.06 | 89.1 | |
| Bi-LSTMParameter=0.2M, Training Set=Augmented (AC)2021.06 | 88.5 | |
| SVM(TF-IDF)Training Set=Combined (C)2021.06 | 87.3 | |
| SVM(TF-IDF)Training Set=Augmented (AC)2021.06 | 86.1 | |
| BERTParameter=110M, Training Set=Original (O)2021.06 | 82.2 | |
| Bi-LSTMParameter=0.2M, Training Set=Original (O)2021.06 | 55.7 | |
| SVM(TF-IDF)Training Set=Original (O)2021.06 | 51 |